⚠️紧急通知：由于火山官方近期在严格自查客户违规转售 API 的行为，当前海外渠道收到官方预警。即日起，先暂停海外seedance API 接口服务，恢复时间另行通知，非常抱歉给您带来不便，感谢理解与支持🙏

提交文本任务(非流式)

POST

https://vg-api.aig-ai.com/v1/{model_id}

目前该模型暂不支持流式调用，接口返回400报错，错误信息：Omni does not support streaming

请求参数

Path 参数

Header 参数

Body 参数application/json必填

示例

{
    "model": "gemini-omni-flash-preview",
    "background": false,
    "input": [
        {
            "type": "user_input",
            "content": [
                {
                    "type": "text",
                    "text": "请介绍一下 Gemini Omni Flash 模型，并说明它适用于哪些场景。"
                }
            ]
        }
    ],
    "generation_config": {
        "thinking_level": "high",
        "thinking_summaries": "auto"
    }
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location 'https://vg-api.aig-ai.com/v1/gemini-omni-flash-preview' \
--header 'Authorization: Bearer sk-abcdefghijklmnopqrstuvwxyz1234567890' \
--header 'Content-Type: application/json' \
--data '{
    "model": "gemini-omni-flash-preview",
    "background": false,
    "input": [
        {
            "type": "user_input",
            "content": [
                {
                    "type": "text",
                    "text": "请介绍一下 Gemini Omni Flash 模型，并说明它适用于哪些场景。"
                }
            ]
        }
    ],
    "generation_config": {
        "thinking_level": "high",
        "thinking_summaries": "auto"
    }
}'

返回响应

🟢200成功

application/json

Bodyapplication/json

示例

{
    "id": "sRJFaqXSMZ7Fvr0PnLW1xxxxx",
    "status": "completed",
    "usage": {
        "total_tokens": 2115,
        "total_input_tokens": 15,
        "input_tokens_by_modality": [
            {
                "modality": "text",
                "tokens": 15
            }
        ],
        "total_output_tokens": 1164,
        "output_tokens_by_modality": [
            {
                "modality": "text",
                "tokens": 1164
            }
        ],
        "total_tool_use_tokens": 0,
        "total_thought_tokens": 936
    },
    "role": "model",
    "created": "2026-07-01T13:14:37Z",
    "updated": "2026-07-01T13:14:37Z",
    "steps": [
        {
            "signature": "[超长字符串 长度=5288] AY89a1/GbwfoKP07DHA/lzBqvCoL7aI/AcMNglV5TJS85jsRoaxtif9ujCMLVLsTWLHzKrdpk4OmXh3r2xOtXllT2JchzgiswtrY...",
            "summary": [
                {
                    "text": "**Explaining the Model**\n\nI need to explain Gemini 1.5 Flash, a fast, cost-effective multimodal model. It excels in speed, large context windows, and multimodal capabilities. It is ideal for real-time customer service, data summarization, and interactive experiences. Developers and startups can use it for cost-effective AI solutions or as a preliminary step before using more powerful models.\n\n\n",
                    "type": "text"
                }
            ],
            "type": "thought"
        },
        {
            "content": [
                {
                    "text": "[超长字符串 长度=2220] 你提到的 **Gemini Omni Flash** 准确来说，在谷歌（Google）官方的命名体系中，通常被称为 **Gemini 1.5 Flash**。\n\n这里的 \"Omni\"（全能/全模态）是...",
                    "type": "text"
                }
            ],
            "type": "model_output"
        }
    ],
    "object": "interaction",
    "model": "gemini-omni-flash-preview"
}

查询视频生成任务（异步）